CN106448654A - Robot speech recognition system and working method thereof - Google Patents
Robot speech recognition system and working method thereof Download PDFInfo
- Publication number
- CN106448654A CN106448654A CN201610874944.0A CN201610874944A CN106448654A CN 106448654 A CN106448654 A CN 106448654A CN 201610874944 A CN201610874944 A CN 201610874944A CN 106448654 A CN106448654 A CN 106448654A
- Authority
- CN
- China
- Prior art keywords
- voice signal
- voice
- module
- robot
- speech
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000001914 filtration Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000000605 extraction Methods 0.000 claims description 13
- 238000009432 framing Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 238000002360 preparation method Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 230000001149 cognitive effect Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 abstract 3
- 238000005516 engineering process Methods 0.000 description 8
- 238000011161 development Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a robot speech recognition system, which comprises a speech input module, a pre-processing module, a feature extracting module, a mode matching module and a recognition result output module which are sequentially connected, wherein a model library is additionally connected to an input end of the mode matching module, and an input end of the model library is connected to an output end of the feature extracting module; and the working system of the system specifically comprises the following steps: speech signal collection, speech signal pre-processing, feature extracting, model training and mode matching. According to the robot speech recognition system and the working method thereof provided by the invention, by conducting a series of treatment on natural language by virtue of the pre-processing module, the feature extracting module, a model training module, the mode matching module and the like, a robot can conduct speech recognition on the natural language, so that recognition accuracy and efficiency are improved; by virtue of such processing measures as filtering and the like, the definition of the speech signals is improved, so that the speech signals are convenient to recognize; and with the application of the speech recognition method, the intelligence level of the robot is improved.
Description
Technical field
The invention belongs to technical field of voice recognition, more particularly to a kind of robot voice identifying system and its work side
Method.
Background technology
With the fast development of computer technology, human society has stepped into the increasingly automated and informationalized epoch.Can
Greatly accelerate the progress of human society with the development saying computer technology.And the progress of human society is in turn to computer
The development of technology is put forward higher requirement and is challenged.The direction that robot is increasingly combined to intellectuality with hommization is developed,
Make people's an urgent demand Voice command robot.
Speech recognition plays in the contacts and the mankind between in terms of man-machine interaction and acts on.In today's society, machine exists
Omnipresent in human being's production life, such as industrial control system, OAS etc., the presence of which is brought for people
More convenient, comfortable and efficient life style.In order that the control of Human-to-Machine and machine are more friendly to the feedback of people
Kind, human needs study intelligentized machine.The most direct, one of convenience, natural communication for information means the voice as people
Then become the important medium of man-machine interaction naturally.Speech recognition is combined with phonetic synthesis, the machine human speech of composition
Sound identifying system can complete the interface of intelligent robot.Language processing techniques and speech recognition technology are just progressively becoming information
The key technology of man-machine interface in technology, in the near future, by the combination of speech recognition technology and speech synthesis technique, people
Just can carry out the former operation needing and just can carrying out using button control by voice command.
Content of the invention
It is an object of the invention to provide a kind of robot voice identifying system and its method of work, answering by this system
With solving the problems, such as that existing conventional machines people's language recognition performance is difficult to satisfy social needs.
For solving above-mentioned technical problem, the present invention is achieved by the following technical solutions：
The present invention be a kind of robot voice identifying system, including the voice input module being sequentially connected, pretreatment module,
Characteristic extracting module, Pattern Matching Module and recognition result output module, the input of described Pattern Matching Module is also associated with
Model library, the input of described model library is connected with the outfan of characteristic extracting module.
Further, described voice input module is used for receiving the voice signal of natural language and being sent to pretreatment
Module；Described pretreatment module is used for the voice signal receiving being carried out with pretreatment and the voice signal after processing being reached spy
Levy extraction module, wherein pretreatment include the pre-filtering of voice signal, the digitized of voice signal, the preemphasis of voice signal,
The end-point detection of the adding window framing, the noise suppressed of voice signal and voice signal of voice signal；Described characteristic extracting module is used
In the extraction that voice signal is carried out with speech characteristic parameter, then the speech characteristic parameter extracting is reached pattern match respectively
Module and model library, wherein phonetic feature include frame feature vector；Described model library is used for the speech characteristic parameter receiving is entered
Row model training, this model training is used for making robot obtain model parameter from substantial amounts of real speech, then forms voice
Reference model storehouse；Described Pattern Matching Module is used for carrying out the model parameter in phonetic feature to be identified and model library
Join, then voice identification result is exported according to matching distance, and voice identification result is reached recognition result output module；Described
Recognition result output module is used for exporting voice identification result.
Further, described voice input module is microphone.
A kind of method of work of robot voice identifying system, the method includes step in detail below：
Step one, the collection of voice signal
Robot receives the voice signal of natural language by its audio sensor；
Step 2, the pretreatment of voice signal
The pretreatment of voice signal includes pre-filtering, the digitized of voice signal, preemphasis, adding window framing, noise suppressed
And end-point detection；The pretreatment of described voice signal is the early stage preparation work of speech recognition process, for follow-up links
Process lays the foundation；
Step 3, feature extraction
Voice signal after step 2 is processed is carried out the extraction of speech characteristic parameter, be voice from phonetic feature
Identify is basic, and wherein phonetic feature is frame feature vector；
Step 4, model training
Voice signal after step 3 is processed is carried out with model training, the purpose of training is to allow robot from substantial amounts of
The necessary model parameter of real speech learning, for forming phonetic reference library, is that cognitive phase is prepared；
Step 5, pattern match
According to certain rule, using model parameter in step 4, pattern match is carried out to the voice of input, and export knowledge
Other result.
Further, pre-filtering described in step 2 is to adopt band filter, and described pre-filtering is used for suppression input letter
Number each frequency domain components medium frequency exceeds institute's power supply power frequency component that is important and suppressing 50Hz or 60Hz of sample frequency half.
Further, the digitized of voice signal described in step 2 includes the sampling of voice signal and the amount of voice signal
Change, first voice signal is sampled, then again voice signal is quantified, then obtain the voice letter of discrete time-domain
Number.
Further, preemphasis described in step 2 is the energy for lifting voice signal medium-high frequency message part, with
Make up the energy loss of the high-frequency signal part producing when lip radiates of sound.
Further, adding window framing described in step 2 is that voice signal is treated to after adding window framing language in short-term
Sound frame, regards stable stochastic signal as each Short Time Speech frame then, then extracts the characteristic vector of voice signal frame by frame,
Obtain the speech characteristic parameter sequence being made up of each frame parameter afterwards.
The invention has the advantages that：
The present invention by carrying out the one of the modules such as pretreatment, feature extraction, model training and pattern match to natural language
Series of processes, so that robot carries out speech recognition to natural language, improves accuracy and the efficiency of identification；By filter
The treatment measures such as ripple, improve the definition of voice signal, consequently facilitating identification；By this audio recognition method, improve machine
The intelligent level of device people.
Certainly, the arbitrary product implementing the present invention it is not absolutely required to reach all the above advantage simultaneously.
Brief description
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, below by use required for embodiment description
Accompanying drawing be briefly described it should be apparent that, drawings in the following description are only some embodiments of the present invention, for ability
For the those of ordinary skill of domain, on the premise of not paying creative work, can also be obtained other attached according to these accompanying drawings
Figure.
Fig. 1 is a kind of composition frame chart of robot voice identifying system of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation description is it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is all other that those of ordinary skill in the art are obtained under the premise of not making creative work
Embodiment, broadly falls into the scope of protection of the invention.
Refer to shown in Fig. 1, the present invention is a kind of robot voice identifying system, including the phonetic entry mould being sequentially connected
Block, pretreatment module, characteristic extracting module, Pattern Matching Module and recognition result output module, the input of Pattern Matching Module
End is also associated with model library, and the input of model library is connected with the outfan of characteristic extracting module.
Wherein, voice input module is used for receiving the voice signal of natural language and being sent to pretreatment module, its
Middle voice input module is microphone；Pretreatment module is used for the voice signal receiving carried out pretreatment and by the language after processing
Message number reaches characteristic extracting module, and wherein pretreatment includes the pre-filtering of voice signal, the digitized of voice signal, voice letter
Number preemphasis, the end-point detection of the adding window framing, the noise suppressed of voice signal and voice signal of voice signal；Feature extraction
Module is used for voice signal is carried out with the extraction of speech characteristic parameter, then the speech characteristic parameter extracting is reached mould respectively
Formula matching module and model library, wherein phonetic feature include frame feature vector；Model library is used for the speech characteristic parameter receiving
Carry out model training, model training is used for making robot obtain model parameter from substantial amounts of real speech, then form voice
Reference model storehouse；Pattern Matching Module is used for being mated phonetic feature to be identified with the model parameter in model library, continues
And voice identification result is exported according to matching distance, and voice identification result is reached recognition result output module；Recognition result
Output module is used for exporting voice identification result.
A kind of method of work of robot voice identifying system, the method includes step in detail below：
Step one, the collection of voice signal
Robot receives the voice signal of natural language by its audio sensor；
Step 2, the pretreatment of voice signal
The pretreatment of voice signal includes pre-filtering, the digitized of voice signal, preemphasis, adding window framing, noise suppressed
And end-point detection；The pretreatment of voice signal is the early stage preparation work of speech recognition process, for the process of follow-up links
Lay the foundation；
Wherein, pre-filtering is to adopt band filter, and the purpose of pre-filtering has two：The first suppresses each frequency of input signal
The institute that domain component medium frequency exceeds sample frequency half is important, to prevent frequency alias from disturbing；Its two be suppression 50Hz or
The power supply Hz noise of 60Hz；
Wherein, the digitized of voice signal includes the sampling of voice signal and the quantization of voice signal, that is, first to voice
Signal is sampled, and then voice signal is quantified again, and then obtains the voice signal of discrete time-domain；
Wherein, preemphasis is the energy for lifting voice signal medium-high frequency message part, with make up sound in lip
The energy loss of the high-frequency signal part producing during radiation；
Wherein, adding window framing is after adding window framing, voice signal to be treated to Short Time Speech frame, then each
Short Time Speech frame regards stable stochastic signal as, then extracts the characteristic vector of voice signal frame by frame, finally obtains by each frame
The speech characteristic parameter sequence of parameter composition；
Step 3, feature extraction
Voice signal after step 2 is processed is carried out the extraction of speech characteristic parameter, be voice from phonetic feature
Identify is basic, and wherein phonetic feature is frame feature vector；
Step 4, model training
Voice signal after step 3 is processed is carried out with model training, the purpose of training is to allow robot from substantial amounts of
The necessary model parameter of real speech learning, for forming phonetic reference library, is that cognitive phase is prepared；
Step 5, pattern match
According to certain rule, using model parameter in step 4, pattern match is carried out to the voice of input, and export knowledge
Other result.
In the description of this specification, the description of reference term " embodiment ", " example ", " specific example " etc. means
It is contained at least one enforcement of the present invention in conjunction with the specific features of this embodiment or example description, structure, material or feature
In example or example.In this manual, identical embodiment or example are not necessarily referring to the schematic representation of above-mentioned term.
And, the specific features of description, structure, material or feature can be to close in any one or more embodiments or example
Suitable mode combines.
Finally it should be noted that present invention disclosed above preferred embodiment is only intended to help illustrate the present invention.Excellent
Select embodiment not have all of details of detailed descriptionthe, also do not limit the specific embodiment that this invention is only described.Obviously, root
According to the content of this specification, can make many modifications and variations.This specification is chosen and is specifically described these embodiments, be in order to
Preferably explain principle and the practical application of the present invention, so that skilled artisan can be best understood by and utilize
The present invention.The present invention is only limited by claims and its four corner and equivalent.
Claims (8)
1. a kind of robot voice identifying system it is characterised in that：Including the voice input module being sequentially connected, pretreatment mould
Block, characteristic extracting module, Pattern Matching Module and recognition result output module, the input of described Pattern Matching Module is also connected with
There is model library, the input of described model library is connected with the outfan of characteristic extracting module.
2. a kind of robot voice identifying system according to claim 1 it is characterised in that：
Described voice input module is used for receiving the voice signal of natural language and being sent to pretreatment module；
Described pretreatment module is used for the voice signal receiving being carried out with pretreatment and the voice signal after processing being reached spy
Levy extraction module, wherein pretreatment include the pre-filtering of voice signal, the digitized of voice signal, the preemphasis of voice signal,
The end-point detection of the adding window framing, the noise suppressed of voice signal and voice signal of voice signal；
Described characteristic extracting module is used for voice signal is carried out with the extraction of speech characteristic parameter, then that the voice extracting is special
Levy parameter and reach Pattern Matching Module and model library respectively, wherein phonetic feature includes frame feature vector；
Described model library is used for carrying out model training to the speech characteristic parameter receiving, and this model training is used for making robot from big
Obtain model parameter in the real speech of amount, then form phonetic reference library；
Described Pattern Matching Module is used for being mated phonetic feature to be identified with the model parameter in model library, root then
Export voice identification result according to matching distance, and voice identification result is reached recognition result output module；Described recognition result
Output module is used for exporting voice identification result.
3. a kind of robot voice identifying system according to claim 1 and 2 it is characterised in that：Described phonetic entry mould
Block is microphone.
4. a kind of method of work of robot voice identifying system as claimed in claim 1 it is characterised in that：The method includes
Step in detail below：
Step one, the collection of voice signal
Robot receives the voice signal of natural language by its audio sensor；
Step 2, the pretreatment of voice signal
The pretreatment of voice signal includes pre-filtering, the digitized of voice signal, preemphasis, adding window framing, noise suppressed and end
Point detection；The pretreatment of described voice signal is the early stage preparation work of speech recognition process, for the process of follow-up links
Lay the foundation；
Step 3, feature extraction
Voice signal after step 2 is processed is carried out the extraction of speech characteristic parameter, be speech recognition from phonetic feature
Basic, wherein phonetic feature be frame feature vector；
Step 4, model training
Voice signal after step 3 is processed is carried out with model training, the purpose of training is to allow robot from substantial amounts of true
The necessary model parameter of voice learning, for forming phonetic reference library, is that cognitive phase is prepared；
Step 5, pattern match
According to certain rule, using model parameter in step 4, pattern match is carried out to the voice of input, and export identification knot
Really.
5. a kind of robot voice identifying system according to claim 4 method of work it is characterised in that：In step 2
Described pre-filtering is to adopt band filter, and described pre-filtering is used for suppressing input signal each frequency domain components medium frequency to exceed sampling
Frequency half important and suppression 50Hz or 60Hz power supply power frequency component.
6. a kind of robot voice identifying system according to claim 4 method of work it is characterised in that：In step 2
The digitized of described voice signal includes the sampling of voice signal and the quantization of voice signal, first voice signal is adopted
Sample, then quantifies to voice signal again, then obtains the voice signal of discrete time-domain.
7. a kind of robot voice identifying system according to claim 4 method of work it is characterised in that：In step 2
Described preemphasis is the energy for lifting voice signal medium-high frequency message part, to make up producing when lip radiates of sound
High-frequency signal part energy loss.
8. a kind of robot voice identifying system according to claim 4 method of work it is characterised in that：In step 2
Described adding window framing is voice signal to be treated to after adding window framing Short Time Speech frame, then each Short Time Speech frame
Regard stable stochastic signal as, then extract the characteristic vector of voice signal frame by frame, finally obtain and be made up of each frame parameter
Speech characteristic parameter sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610874944.0A CN106448654A (en) | 2016-09-30 | 2016-09-30 | Robot speech recognition system and working method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610874944.0A CN106448654A (en) | 2016-09-30 | 2016-09-30 | Robot speech recognition system and working method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106448654A true CN106448654A (en) | 2017-02-22 |
Family
ID=58171932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610874944.0A Pending CN106448654A (en) | 2016-09-30 | 2016-09-30 | Robot speech recognition system and working method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106448654A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107329996A (en) * | 2017-06-08 | 2017-11-07 | 三峡大学 | A kind of chat robots system and chat method based on fuzzy neural network |
| CN107742519A (en) * | 2017-10-31 | 2018-02-27 | 珠海市美瑞华医用科技有限公司 | A kind of voice entry system of intelligent control fluid delivery apparatus |
| CN108320746A (en) * | 2018-02-09 | 2018-07-24 | 杭州智仁建筑工程有限公司 | A kind of intelligent domestic system |
| CN108550394A (en) * | 2018-03-12 | 2018-09-18 | 广州势必可赢网络科技有限公司 | A kind of method and device of diagnosing a disease based on Application on Voiceprint Recognition |
| CN108922535A (en) * | 2018-08-23 | 2018-11-30 | 上海华测导航技术股份有限公司 | Voice interactive system and exchange method for receiver |
| CN109036387A (en) * | 2018-07-16 | 2018-12-18 | 中央民族大学 | Video speech recognition methods and system |
| CN109087646A (en) * | 2018-10-25 | 2018-12-25 | 武汉拓睿传奇科技有限公司 | A kind of importing artificial intelligence is ultra-deep to be learnt to know method for distinguishing for phonetic image |
| CN109243458A (en) * | 2018-11-22 | 2019-01-18 | 苏州米机器人有限公司 | A kind of speech recognition system for intelligent robot |
| CN109545220A (en) * | 2019-01-15 | 2019-03-29 | 安徽大尺度网络传媒有限公司 | A kind of artificial intelligent voice identifying system |
| CN109637544A (en) * | 2018-12-25 | 2019-04-16 | 它酷科技(大连)有限公司 | A kind of language control method of emulated robot |
| CN110085212A (en) * | 2019-04-04 | 2019-08-02 | 浙江工业大学之江学院 | A kind of audio recognition method for CNC program controller |
| CN111179925A (en) * | 2019-12-04 | 2020-05-19 | 北京永洪商智科技有限公司 | Report layout system and method based on voice recognition |
| CN111681659A (en) * | 2020-06-08 | 2020-09-18 | 北京高因科技有限公司 | Automatic voice recognition system applied to portable equipment and working method thereof |
| CN112732881A (en) * | 2020-12-30 | 2021-04-30 | 深圳市天策规划设计有限公司 | Multifunctional indexing system applied to business complex |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101923855A (en) * | 2009-06-17 | 2010-12-22 | 复旦大学 | Test-irrelevant voice print identifying system |
| CN103236260A (en) * | 2013-03-29 | 2013-08-07 | 京东方科技集团股份有限公司 | Voice recognition system |
| CN103903619A (en) * | 2012-12-28 | 2014-07-02 | 安徽科大讯飞信息科技股份有限公司 | Method and system for improving accuracy of speech recognition |
| CN104392718A (en) * | 2014-11-26 | 2015-03-04 | 河海大学 | Robust voice recognition method based on acoustic model array |
| US9881616B2 (en) * | 2012-06-06 | 2018-01-30 | Qualcomm Incorporated | Method and systems having improved speech recognition |
-
2016
- 2016-09-30 CN CN201610874944.0A patent/CN106448654A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101923855A (en) * | 2009-06-17 | 2010-12-22 | 复旦大学 | Test-irrelevant voice print identifying system |
| US9881616B2 (en) * | 2012-06-06 | 2018-01-30 | Qualcomm Incorporated | Method and systems having improved speech recognition |
| CN103903619A (en) * | 2012-12-28 | 2014-07-02 | 安徽科大讯飞信息科技股份有限公司 | Method and system for improving accuracy of speech recognition |
| CN103236260A (en) * | 2013-03-29 | 2013-08-07 | 京东方科技集团股份有限公司 | Voice recognition system |
| CN104392718A (en) * | 2014-11-26 | 2015-03-04 | 河海大学 | Robust voice recognition method based on acoustic model array |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107329996A (en) * | 2017-06-08 | 2017-11-07 | 三峡大学 | A kind of chat robots system and chat method based on fuzzy neural network |
| CN107742519A (en) * | 2017-10-31 | 2018-02-27 | 珠海市美瑞华医用科技有限公司 | A kind of voice entry system of intelligent control fluid delivery apparatus |
| CN108320746B (en) * | 2018-02-09 | 2020-11-10 | 北京国安电气有限责任公司 | Intelligent home system |
| CN108320746A (en) * | 2018-02-09 | 2018-07-24 | 杭州智仁建筑工程有限公司 | A kind of intelligent domestic system |
| CN108550394A (en) * | 2018-03-12 | 2018-09-18 | 广州势必可赢网络科技有限公司 | A kind of method and device of diagnosing a disease based on Application on Voiceprint Recognition |
| CN109036387A (en) * | 2018-07-16 | 2018-12-18 | 中央民族大学 | Video speech recognition methods and system |
| CN108922535A (en) * | 2018-08-23 | 2018-11-30 | 上海华测导航技术股份有限公司 | Voice interactive system and exchange method for receiver |
| CN109087646A (en) * | 2018-10-25 | 2018-12-25 | 武汉拓睿传奇科技有限公司 | A kind of importing artificial intelligence is ultra-deep to be learnt to know method for distinguishing for phonetic image |
| CN109087646B (en) * | 2018-10-25 | 2021-04-06 | 武汉拓睿传奇科技有限公司 | Method for leading-in artificial intelligence ultra-deep learning for voice image recognition |
| CN109243458A (en) * | 2018-11-22 | 2019-01-18 | 苏州米机器人有限公司 | A kind of speech recognition system for intelligent robot |
| CN109637544A (en) * | 2018-12-25 | 2019-04-16 | 它酷科技(大连)有限公司 | A kind of language control method of emulated robot |
| CN109545220A (en) * | 2019-01-15 | 2019-03-29 | 安徽大尺度网络传媒有限公司 | A kind of artificial intelligent voice identifying system |
| CN110085212A (en) * | 2019-04-04 | 2019-08-02 | 浙江工业大学之江学院 | A kind of audio recognition method for CNC program controller |
| CN111179925A (en) * | 2019-12-04 | 2020-05-19 | 北京永洪商智科技有限公司 | Report layout system and method based on voice recognition |
| CN111681659A (en) * | 2020-06-08 | 2020-09-18 | 北京高因科技有限公司 | Automatic voice recognition system applied to portable equipment and working method thereof |
| CN112732881A (en) * | 2020-12-30 | 2021-04-30 | 深圳市天策规划设计有限公司 | Multifunctional indexing system applied to business complex |
| CN112732881B (en) * | 2020-12-30 | 2024-02-27 | 深圳市天策规划设计有限公司 | Multifunctional index system applied to commercial complex |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106448654A (en) | Robot speech recognition system and working method thereof | |
| CN104570835B (en) | Aircraft cockpit phonetic order control system and its operating method | |
| CN102737629B (en) | Embedded type speech emotion recognition method and device | |
| CN106898350A (en) | A kind of interaction of intelligent industrial robot voice and control method based on deep learning | |
| CN105810213A (en) | Typical abnormal sound detection method and device | |
| CN105261356A (en) | Voice recognition system and method | |
| CN102298694A (en) | Man-machine interaction identification system applied to remote information service | |
| CN103422764A (en) | Door control system and control method thereof | |
| CN202542604U (en) | Speech recognition man-machine interaction device for elevator | |
| CN105006230A (en) | Voice sensitive information detecting and filtering method based on unspecified people | |
| CN103543979A (en) | Voice outputting method, voice interaction method and electronic device | |
| CN107845381A (en) | A kind of method and system of robot semantic processes | |
| CN106448657A (en) | Continuous speech recognition system for restaurant robot servant | |
| CN106887227A (en) | A kind of voice awakening method and system | |
| CN106683676A (en) | Voice recognition system for robot control | |
| Wang et al. | Research on speech emotion recognition technology based on deep and shallow neural network | |
| CN108172220B (en) | Novel voice denoising method | |
| CN106653020A (en) | Multi-business control method and system for smart sound and video equipment based on deep learning | |
| CN112017658A (en) | Operation control system based on intelligent human-computer interaction | |
| CN111105798B (en) | Equipment control method based on voice recognition | |
| CN204695292U (en) | The identification switching device shifter of the online and off-line that robot predicts based on dialogue | |
| CN106448676A (en) | Robot speech recognition system based on natural language processing | |
| CN105070291A (en) | Sound control door system based on dynamic time warping technology | |
| CN108091327A (en) | A kind of intelligent sound apparatus control method | |
| CN111192573B (en) | Intelligent control method for equipment based on voice recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170222 |
|
| RJ01 | Rejection of invention patent application after publication |